Results 141 to 150 of about 3,102,730 (292)
Exact Discrete Stochastic Simulation With Deep‐Learning‐Scale Gradient Optimization
A 203,796‐parameter gene regulatory network classifies handwritten digits with 98.4% accuracy using exact stochastic dynamics. The framework decouples forward simulation from backward differentiation, making continuous‐time Markov chain models compatible with deep‐learning optimization.
Jose M. G. Vilar, Leonor Saiz
wiley +1 more source
Spatial Bayesian neural networks
35 pages, 21 ...
Andrew Zammit-Mangion +4 more
openaire +4 more sources
Large‐scale UK Biobank analyses identify clinical and proteomic signatures for early prediction of valvular heart disease and its subtypes. Proteins add predictive value for VHD, AVS, and MVR, with outcome‐specific compact panels showing translational potential. Multi‐layer evidence highlights matrix remodeling, protease regulation, immune inflammation,
Zhihao Jiang +10 more
wiley +1 more source
Multiscale Circuit Architecture Associated With Memory Dysfunction in Temporal Lobe Epilepsy
A multiscale precision‐mapping framework reveals that memory impairment in temporal lobe epilepsy arises from the convergence of focal medial temporal pathology, strategic white matter disconnection, and limbic‐centered metabolic network dysfunction.
Jiajie Mo +12 more
wiley +1 more source
Caspofungin heteroresistance is prevalent in clinical Candida glabrata isolates and depends on calcineurin‐mediated stress adaptation. This transient phenotype serves as a reservoir for resistance evolution, enabling the emergence of stable resistant descendants under prolonged drug pressure.
Yanyu Su +7 more
wiley +1 more source
Bayesian MAP model selection of chain event graphs [PDF]
The class of chain event graph models is a generalisation of the class of discrete Bayesian networks, retaining most of the structural advantages of the Bayesian network for model interrogation, propagation and learning, while more naturally encoding ...
Freeman, Guy, Smith, J. Q.
core
Transformers are Bayesian Networks
Transformers are the dominant architecture in AI, yet why they work remains poorly understood. This paper offers a precise answer: a transformer is a Bayesian network. We establish this in five ways. First, we prove that every sigmoid transformer with any weights implements weighted loopy belief propagation on its implicit factor graph.
openaire +3 more sources
StackingNet: Collective Inference Across Independent AI Foundation Models
ABSTRACT Artificial intelligence (AI) built on large foundation models has transformed language understanding, computer vision, and reasoning, yet these systems remain isolated and cannot readily share their capabilities. Coordinating the complementary strengths of independently developed, black‐box foundation models is essential for trustworthy ...
Siyang Li +4 more
wiley +1 more source
To accelerate the inverse design of heterostructured metal matrix composites, a closed‐loop scientific machine learning framework integrates continual learning prediction with NSGA‐II‐PMCP optimization. The framework maps microstructural descriptors to strength, toughness, and modulus, expands high‐quality Pareto solutions, and guides experimentally ...
Zhiyan Zhong +11 more
wiley +1 more source
Optimising ITS behaviour with Bayesian networks and decision theory [PDF]
We propose and demonstrate a methodology for building tractable normative intelligent tutoring systems (ITSs). A normative ITS uses a Bayesian network for long-term student modelling and decision theory to select the next tutorial action.
Mitrovic, Antonija, Mayo, Michael
core +1 more source

